{"mean_reward": -0.8550338368862868, "std_reward": 1.0474947112504422, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-14T16:49:24.134929"} |
{"mean_reward": -0.8550338368862868, "std_reward": 1.0474947112504422, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-14T16:49:24.134929"} |